From 2dc75d3c3b49c64fd26b4832a7efb75546cb3fc5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 11 Sep 2008 14:20:23 +0200 Subject: block: disable sysfs parts of the disk command filter We still have life time issues with the sysfs command filter kobject, so disable it for 2.6.27 release. We can revisit this and make it work properly for 2.6.28, for 2.6.27 release it's too risky. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 44710d7e7bff..53ea933cf60b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -843,8 +843,6 @@ extern int blkdev_issue_flush(struct block_device *, sector_t *); */ extern int blk_verify_command(struct blk_cmd_filter *filter, unsigned char *cmd, int has_write_perm); -extern int blk_register_filter(struct gendisk *disk); -extern void blk_unregister_filter(struct gendisk *disk); extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter); #define MAX_PHYS_SEGMENTS 128 -- cgit v1.2.3 From 97b697a11b07e2ebfa69c488132596cc5eb24119 Mon Sep 17 00:00:00 2001 From: Taisuke Yamada Date: Sat, 13 Sep 2008 16:46:15 -0400 Subject: [libata] LBA28/LBA48 off-by-one bug in ata.h I recently bought 3 HGST P7K500-series 500GB SATA drives and had trouble accessing the block right on the LBA28-LBA48 border. Here's how it fails (same for all 3 drives): # dd if=/dev/sdc bs=512 count=1 skip=268435455 > /dev/null dd: reading `/dev/sdc': Input/output error 0+0 records in 0+0 records out 0 bytes (0 B) copied, 0.288033 seconds, 0.0 kB/s # dmesg ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x0 ata1.00: BMDMA stat 0x25 ata1.00: cmd c8/00:08:f8:ff:ff/00:00:00:00:00/ef tag 0 dma 4096 in res 51/04:08:f8:ff:ff/00:00:00:00:00/ef Emask 0x1 (device error) ata1.00: status: { DRDY ERR } ata1.00: error: { ABRT } ata1.00: configured for UDMA/33 ata1: EH complete ... After some investigations, it turned out this seems to be caused by misinterpretation of the ATA specification on LBA28 access. Following part is the code in question: === include/linux/ata.h === static inline int lba_28_ok(u64 block, u32 n_block) { /* check the ending block number */ return ((block + n_block - 1) < ((u64)1 << 28)) && (n_block <= 256); } HGST drive (sometimes) fails with LBA28 access of {block = 0xfffffff, n_block = 1}, and this behavior seems to be comformant. Other drives, including other HGST drives are not that strict, through. >From the ATA specification: (http://www.t13.org/Documents/UploadedDocuments/project/d1410r3b-ATA-ATAPI-6.pdf) 8.15.29 Word (61:60): Total number of user addressable sectors This field contains a value that is one greater than the total number of user addressable sectors (see 6.2). The maximum value that shall be placed in this field is 0FFFFFFFh. So the driver shouldn't use the value of 0xfffffff for LBA28 request as this exceeds maximum user addressable sector. The logical maximum value for LBA28 is 0xffffffe. The obvious fix is to cut "- 1" part, and the patch attached just do that. I've been using the patched kernel for about a month now, and the same fix is also floating on the net for some time. So I believe this fix works reliably. Just FYI, many Windows/Intel platform users also seems to be struck by this, and HGST has issued a note pointing to Intel ICH8/9 driver. "28-bit LBA command is being used to access LBAs 29-bits in length" http://www.hitachigst.com/hddt/knowtree.nsf/cffe836ed7c12018862565b000530c74/b531b8bce8745fb78825740f00580e23 Also, *BSDs seems to have similar fix included sometime around ~2004, through I have not checked out exact portion of the code. Signed-off-by: Taisuke Yamada Signed-off-by: Jeff Garzik --- include/linux/ata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 1ce19c1ef0e9..8a12d718c169 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -745,7 +745,7 @@ static inline int ata_ok(u8 status) static inline int lba_28_ok(u64 block, u32 n_block) { /* check the ending block number */ - return ((block + n_block - 1) < ((u64)1 << 28)) && (n_block <= 256); + return ((block + n_block) < ((u64)1 << 28)) && (n_block <= 256); } static inline int lba_48_ok(u64 block, u32 n_block) -- cgit v1.2.3 From dea420ce0e2973e8ef1fd11fde6804c8d03a82ad Mon Sep 17 00:00:00 2001 From: Hiroshi DOYU Date: Sat, 13 Sep 2008 02:33:07 -0700 Subject: include/linux/ioport.h: add missing macro argument for devm_release_* family akpm: these have no callers at this time, but they shall soon, so let's get them right. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Hiroshi DOYU Cc: Tony Lindgren Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ioport.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 8d3b7a9afd17..350033e8f4e1 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -159,9 +159,9 @@ extern struct resource * __devm_request_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n, const char *name); -#define devm_release_region(start,n) \ +#define devm_release_region(dev, start, n) \ __devm_release_region(dev, &ioport_resource, (start), (n)) -#define devm_release_mem_region(start,n) \ +#define devm_release_mem_region(dev, start, n) \ __devm_release_region(dev, &iomem_resource, (start), (n)) extern void __devm_release_region(struct device *dev, struct resource *parent, -- cgit v1.2.3 From 5bead2a0680687b9576d57c177988e8aa082b922 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Sat, 13 Sep 2008 02:33:19 -0700 Subject: mm: mark the correct zone as full when scanning zonelists The iterator for_each_zone_zonelist() uses a struct zoneref *z cursor when scanning zonelists to keep track of where in the zonelist it is. The zoneref that is returned corresponds to the the next zone that is to be scanned, not the current one. It was intended to be treated as an opaque list. When the page allocator is scanning a zonelist, it marks elements in the zonelist corresponding to zones that are temporarily full. As the zonelist is being updated, it uses the cursor here; if (NUMA_BUILD) zlc_mark_zone_full(zonelist, z); This is intended to prevent rescanning in the near future but the zoneref cursor does not correspond to the zone that has been found to be full. This is an easy misunderstanding to make so this patch corrects the problem by changing zoneref cursor to be the current zone being scanned instead of the next one. Signed-off-by: Mel Gorman Cc: Andy Whitcroft Cc: KAMEZAWA Hiroyuki Cc: [2.6.26.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 12 ++++++------ mm/mmzone.c | 2 +- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 443bc7cd8c62..428328a05fa1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -751,8 +751,9 @@ static inline int zonelist_node_idx(struct zoneref *zoneref) * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the - * search. The zoneref returned is a cursor that is used as the next starting - * point for future calls to next_zones_zonelist(). + * search. The zoneref returned is a cursor that represents the current zone + * being examined. It should be advanced by one before calling + * next_zones_zonelist again. */ struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, @@ -768,9 +769,8 @@ struct zoneref *next_zones_zonelist(struct zoneref *z, * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be - * used to iterate the zonelist with next_zones_zonelist. The cursor should - * not be used by the caller as it does not match the value of the zone - * returned. + * used to iterate the zonelist with next_zones_zonelist by advancing it by + * one before calling. */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, @@ -795,7 +795,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone); \ zone; \ - z = next_zones_zonelist(z, highidx, nodemask, &zone)) \ + z = next_zones_zonelist(++z, highidx, nodemask, &zone)) \ /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index diff --git a/mm/mmzone.c b/mm/mmzone.c index 486ed595ee6f..16ce8b955dcf 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -69,6 +69,6 @@ struct zoneref *next_zones_zonelist(struct zoneref *z, (z->zone && !zref_in_nodemask(z, nodes))) z++; - *zone = zonelist_zone(z++); + *zone = zonelist_zone(z); return z; } -- cgit v1.2.3 From 8e82f8c34b1759ae0d80fe96101746ec51fb1ba4 Mon Sep 17 00:00:00 2001 From: Alex Dubov Date: Sat, 13 Sep 2008 02:33:26 -0700 Subject: memstick: fix MSProHG 8-bit interface mode support - 8-bit interface mode never worked properly. The only adapter I have which supports the 8b mode (the Jmicron) had some problems with its clock wiring and they discovered it only now. We also discovered that ProHG media is more sensitive to the ordering of initialization commands. - Make the driver fall back to highest supported mode instead of always falling back to serial. The driver will attempt the switch to 8b mode for any new MSPro card, but not all of them support it. Previously, these new cards ended up in serial mode, which is not the best idea (they work fine with 4b, after all). - Edit some macros for better conformance to Sony documentation Signed-off-by: Alex Dubov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/memstick/core/memstick.c | 10 ++-- drivers/memstick/core/mspro_block.c | 33 ++++++++++--- drivers/memstick/host/jmb38x_ms.c | 39 ++++++++++----- include/linux/memstick.h | 97 +++++++++++++++++++------------------ 4 files changed, 106 insertions(+), 73 deletions(-) (limited to 'include/linux') diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index a38005008a20..cea46906408e 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -185,7 +185,7 @@ static void memstick_free(struct device *dev) } static struct class memstick_host_class = { - .name = "memstick_host", + .name = "memstick_host", .dev_release = memstick_free }; @@ -264,7 +264,7 @@ EXPORT_SYMBOL(memstick_new_req); * @sg - TPC argument */ void memstick_init_req_sg(struct memstick_request *mrq, unsigned char tpc, - struct scatterlist *sg) + const struct scatterlist *sg) { mrq->tpc = tpc; if (tpc & 8) @@ -294,7 +294,7 @@ EXPORT_SYMBOL(memstick_init_req_sg); * user supplied buffer. */ void memstick_init_req(struct memstick_request *mrq, unsigned char tpc, - void *buf, size_t length) + const void *buf, size_t length) { mrq->tpc = tpc; if (tpc & 8) @@ -439,7 +439,7 @@ static void memstick_check(struct work_struct *work) if (!host->card) { if (memstick_power_on(host)) goto out_power_off; - } else + } else if (host->card->stop) host->card->stop(host->card); card = memstick_alloc_card(host); @@ -458,7 +458,7 @@ static void memstick_check(struct work_struct *work) || !(host->card->check(host->card))) { device_unregister(&host->card->dev); host->card = NULL; - } else + } else if (host->card->start) host->card->start(host->card); } diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index 44b1817f2f2f..d2d2318dafa4 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -30,6 +30,8 @@ module_param(major, int, 0644); #define MSPRO_BLOCK_SIGNATURE 0xa5c3 #define MSPRO_BLOCK_MAX_ATTRIBUTES 41 +#define MSPRO_BLOCK_PART_SHIFT 3 + enum { MSPRO_BLOCK_ID_SYSINFO = 0x10, MSPRO_BLOCK_ID_MODELNAME = 0x15, @@ -195,7 +197,7 @@ static int mspro_block_bd_open(struct inode *inode, struct file *filp) static int mspro_block_disk_release(struct gendisk *disk) { struct mspro_block_data *msb = disk->private_data; - int disk_id = disk->first_minor >> MEMSTICK_PART_SHIFT; + int disk_id = disk->first_minor >> MSPRO_BLOCK_PART_SHIFT; mutex_lock(&mspro_block_disk_lock); @@ -877,6 +879,7 @@ static int mspro_block_switch_interface(struct memstick_dev *card) struct mspro_block_data *msb = memstick_get_drvdata(card); int rc = 0; +try_again: if (msb->caps & MEMSTICK_CAP_PAR4) rc = mspro_block_set_interface(card, MEMSTICK_SYS_PAR4); else @@ -930,6 +933,18 @@ static int mspro_block_switch_interface(struct memstick_dev *card) rc = memstick_set_rw_addr(card); if (!rc) rc = mspro_block_set_interface(card, msb->system); + + if (!rc) { + msleep(150); + rc = mspro_block_wait_for_ced(card); + if (rc) + return rc; + + if (msb->caps & MEMSTICK_CAP_PAR8) { + msb->caps &= ~MEMSTICK_CAP_PAR8; + goto try_again; + } + } } return rc; } @@ -1117,14 +1132,16 @@ static int mspro_block_init_card(struct memstick_dev *card) return -EIO; msb->caps = host->caps; - rc = mspro_block_switch_interface(card); + + msleep(150); + rc = mspro_block_wait_for_ced(card); if (rc) return rc; - msleep(200); - rc = mspro_block_wait_for_ced(card); + rc = mspro_block_switch_interface(card); if (rc) return rc; + dev_dbg(&card->dev, "card activated\n"); if (msb->system != MEMSTICK_SYS_SERIAL) msb->caps |= MEMSTICK_CAP_AUTO_GET_INT; @@ -1192,12 +1209,12 @@ static int mspro_block_init_disk(struct memstick_dev *card) if (rc) return rc; - if ((disk_id << MEMSTICK_PART_SHIFT) > 255) { + if ((disk_id << MSPRO_BLOCK_PART_SHIFT) > 255) { rc = -ENOSPC; goto out_release_id; } - msb->disk = alloc_disk(1 << MEMSTICK_PART_SHIFT); + msb->disk = alloc_disk(1 << MSPRO_BLOCK_PART_SHIFT); if (!msb->disk) { rc = -ENOMEM; goto out_release_id; @@ -1220,7 +1237,7 @@ static int mspro_block_init_disk(struct memstick_dev *card) MSPRO_BLOCK_MAX_PAGES * msb->page_size); msb->disk->major = major; - msb->disk->first_minor = disk_id << MEMSTICK_PART_SHIFT; + msb->disk->first_minor = disk_id << MSPRO_BLOCK_PART_SHIFT; msb->disk->fops = &ms_block_bdops; msb->usage_count = 1; msb->disk->private_data = msb; @@ -1416,7 +1433,7 @@ out_unlock: static struct memstick_device_id mspro_block_id_tbl[] = { {MEMSTICK_MATCH_ALL, MEMSTICK_TYPE_PRO, MEMSTICK_CATEGORY_STORAGE_DUO, - MEMSTICK_CLASS_GENERIC_DUO}, + MEMSTICK_CLASS_DUO}, {} }; diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c index 3485c63d20b0..2fb95a5b72eb 100644 --- a/drivers/memstick/host/jmb38x_ms.c +++ b/drivers/memstick/host/jmb38x_ms.c @@ -81,6 +81,8 @@ struct jmb38x_ms { #define TPC_CODE_SZ_MASK 0x00000700 #define TPC_DATA_SZ_MASK 0x00000007 +#define HOST_CONTROL_TDELAY_EN 0x00040000 +#define HOST_CONTROL_HW_OC_P 0x00010000 #define HOST_CONTROL_RESET_REQ 0x00008000 #define HOST_CONTROL_REI 0x00004000 #define HOST_CONTROL_LED 0x00000400 @@ -88,6 +90,7 @@ struct jmb38x_ms { #define HOST_CONTROL_RESET 0x00000100 #define HOST_CONTROL_POWER_EN 0x00000080 #define HOST_CONTROL_CLOCK_EN 0x00000040 +#define HOST_CONTROL_REO 0x00000008 #define HOST_CONTROL_IF_SHIFT 4 #define HOST_CONTROL_IF_SERIAL 0x0 @@ -133,11 +136,15 @@ struct jmb38x_ms { #define PAD_PU_PD_ON_MS_SOCK1 0x0f0f0000 #define CLOCK_CONTROL_40MHZ 0x00000001 -#define CLOCK_CONTROL_50MHZ 0x00000002 +#define CLOCK_CONTROL_50MHZ 0x0000000a #define CLOCK_CONTROL_60MHZ 0x00000008 #define CLOCK_CONTROL_62_5MHZ 0x0000000c #define CLOCK_CONTROL_OFF 0x00000000 +#define PCI_CTL_CLOCK_DLY_ADDR 0x000000b0 +#define PCI_CTL_CLOCK_DLY_MASK_A 0x00000f00 +#define PCI_CTL_CLOCK_DLY_MASK_B 0x0000f000 + enum { CMD_READY = 0x01, FIFO_READY = 0x02, @@ -367,8 +374,7 @@ static int jmb38x_ms_issue_cmd(struct memstick_host *msh) return host->req->error; } - dev_dbg(&msh->dev, "control %08x\n", - readl(host->addr + HOST_CONTROL)); + dev_dbg(&msh->dev, "control %08x\n", readl(host->addr + HOST_CONTROL)); dev_dbg(&msh->dev, "status %08x\n", readl(host->addr + INT_STATUS)); dev_dbg(&msh->dev, "hstatus %08x\n", readl(host->addr + STATUS)); @@ -637,7 +643,7 @@ static int jmb38x_ms_reset(struct jmb38x_ms_host *host) ndelay(20); } dev_dbg(&host->chip->pdev->dev, "reset_req timeout\n"); - return -EIO; + /* return -EIO; */ reset_next: writel(HOST_CONTROL_RESET | HOST_CONTROL_CLOCK_EN @@ -680,7 +686,9 @@ static int jmb38x_ms_set_param(struct memstick_host *msh, host_ctl = 7; host_ctl |= HOST_CONTROL_POWER_EN - | HOST_CONTROL_CLOCK_EN; + | HOST_CONTROL_CLOCK_EN + | HOST_CONTROL_HW_OC_P + | HOST_CONTROL_TDELAY_EN; writel(host_ctl, host->addr + HOST_CONTROL); writel(host->id ? PAD_PU_PD_ON_MS_SOCK1 @@ -704,33 +712,40 @@ static int jmb38x_ms_set_param(struct memstick_host *msh, break; case MEMSTICK_INTERFACE: host_ctl &= ~(3 << HOST_CONTROL_IF_SHIFT); + pci_read_config_dword(host->chip->pdev, + PCI_CTL_CLOCK_DLY_ADDR, + &clock_delay); + clock_delay &= host->id ? ~PCI_CTL_CLOCK_DLY_MASK_B + : ~PCI_CTL_CLOCK_DLY_MASK_A; if (value == MEMSTICK_SERIAL) { host_ctl &= ~HOST_CONTROL_FAST_CLK; + host_ctl &= ~HOST_CONTROL_REO; host_ctl |= HOST_CONTROL_IF_SERIAL << HOST_CONTROL_IF_SHIFT; host_ctl |= HOST_CONTROL_REI; clock_ctl = CLOCK_CONTROL_40MHZ; - clock_delay = 0; } else if (value == MEMSTICK_PAR4) { - host_ctl |= HOST_CONTROL_FAST_CLK; + host_ctl |= HOST_CONTROL_FAST_CLK | HOST_CONTROL_REO; host_ctl |= HOST_CONTROL_IF_PAR4 << HOST_CONTROL_IF_SHIFT; host_ctl &= ~HOST_CONTROL_REI; clock_ctl = CLOCK_CONTROL_40MHZ; - clock_delay = 4; + clock_delay |= host->id ? (4 << 12) : (4 << 8); } else if (value == MEMSTICK_PAR8) { host_ctl |= HOST_CONTROL_FAST_CLK; host_ctl |= HOST_CONTROL_IF_PAR8 << HOST_CONTROL_IF_SHIFT; - host_ctl &= ~HOST_CONTROL_REI; - clock_ctl = CLOCK_CONTROL_60MHZ; - clock_delay = 0; + host_ctl &= ~(HOST_CONTROL_REI | HOST_CONTROL_REO); + clock_ctl = CLOCK_CONTROL_50MHZ; } else return -EINVAL; + writel(host_ctl, host->addr + HOST_CONTROL); writel(clock_ctl, host->addr + CLOCK_CONTROL); - writel(clock_delay, host->addr + CLOCK_DELAY); + pci_write_config_dword(host->chip->pdev, + PCI_CTL_CLOCK_DLY_ADDR, + clock_delay); break; }; return 0; diff --git a/include/linux/memstick.h b/include/linux/memstick.h index a9f998a3f48b..d0c37e682234 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -21,30 +21,30 @@ struct ms_status_register { unsigned char reserved; unsigned char interrupt; -#define MEMSTICK_INT_CMDNAK 0x0001 -#define MEMSTICK_INT_IOREQ 0x0008 -#define MEMSTICK_INT_IOBREQ 0x0010 -#define MEMSTICK_INT_BREQ 0x0020 -#define MEMSTICK_INT_ERR 0x0040 -#define MEMSTICK_INT_CED 0x0080 +#define MEMSTICK_INT_CMDNAK 0x01 +#define MEMSTICK_INT_IOREQ 0x08 +#define MEMSTICK_INT_IOBREQ 0x10 +#define MEMSTICK_INT_BREQ 0x20 +#define MEMSTICK_INT_ERR 0x40 +#define MEMSTICK_INT_CED 0x80 unsigned char status0; -#define MEMSTICK_STATUS0_WP 0x0001 -#define MEMSTICK_STATUS0_SL 0x0002 -#define MEMSTICK_STATUS0_BF 0x0010 -#define MEMSTICK_STATUS0_BE 0x0020 -#define MEMSTICK_STATUS0_FB0 0x0040 -#define MEMSTICK_STATUS0_MB 0x0080 +#define MEMSTICK_STATUS0_WP 0x01 +#define MEMSTICK_STATUS0_SL 0x02 +#define MEMSTICK_STATUS0_BF 0x10 +#define MEMSTICK_STATUS0_BE 0x20 +#define MEMSTICK_STATUS0_FB0 0x40 +#define MEMSTICK_STATUS0_MB 0x80 unsigned char status1; -#define MEMSTICK_STATUS1_UCFG 0x0001 -#define MEMSTICK_STATUS1_FGER 0x0002 -#define MEMSTICK_STATUS1_UCEX 0x0004 -#define MEMSTICK_STATUS1_EXER 0x0008 -#define MEMSTICK_STATUS1_UCDT 0x0010 -#define MEMSTICK_STATUS1_DTER 0x0020 -#define MEMSTICK_STATUS1_FBI 0x0040 -#define MEMSTICK_STATUS1_MB 0x0080 +#define MEMSTICK_STATUS1_UCFG 0x01 +#define MEMSTICK_STATUS1_FGER 0x02 +#define MEMSTICK_STATUS1_UCEX 0x04 +#define MEMSTICK_STATUS1_EXER 0x08 +#define MEMSTICK_STATUS1_UCDT 0x10 +#define MEMSTICK_STATUS1_DTER 0x20 +#define MEMSTICK_STATUS1_FB1 0x40 +#define MEMSTICK_STATUS1_MB 0x80 } __attribute__((packed)); struct ms_id_register { @@ -56,32 +56,32 @@ struct ms_id_register { struct ms_param_register { unsigned char system; -#define MEMSTICK_SYS_ATEN 0xc0 -#define MEMSTICK_SYS_BAMD 0x80 #define MEMSTICK_SYS_PAM 0x08 +#define MEMSTICK_SYS_BAMD 0x80 unsigned char block_address_msb; unsigned short block_address; unsigned char cp; -#define MEMSTICK_CP_BLOCK 0x0000 -#define MEMSTICK_CP_PAGE 0x0020 -#define MEMSTICK_CP_EXTRA 0x0040 -#define MEMSTICK_CP_OVERWRITE 0x0080 +#define MEMSTICK_CP_BLOCK 0x00 +#define MEMSTICK_CP_PAGE 0x20 +#define MEMSTICK_CP_EXTRA 0x40 +#define MEMSTICK_CP_OVERWRITE 0x80 unsigned char page_address; } __attribute__((packed)); struct ms_extra_data_register { unsigned char overwrite_flag; -#define MEMSTICK_OVERWRITE_UPDATA 0x0010 -#define MEMSTICK_OVERWRITE_PAGE 0x0060 -#define MEMSTICK_OVERWRITE_BLOCK 0x0080 +#define MEMSTICK_OVERWRITE_UDST 0x10 +#define MEMSTICK_OVERWRITE_PGST1 0x20 +#define MEMSTICK_OVERWRITE_PGST0 0x40 +#define MEMSTICK_OVERWRITE_BKST 0x80 unsigned char management_flag; -#define MEMSTICK_MANAGEMENT_SYSTEM 0x0004 -#define MEMSTICK_MANAGEMENT_TRANS_TABLE 0x0008 -#define MEMSTICK_MANAGEMENT_COPY 0x0010 -#define MEMSTICK_MANAGEMENT_ACCESS 0x0020 +#define MEMSTICK_MANAGEMENT_SYSFLG 0x04 +#define MEMSTICK_MANAGEMENT_ATFLG 0x08 +#define MEMSTICK_MANAGEMENT_SCMS1 0x10 +#define MEMSTICK_MANAGEMENT_SCMS0 0x20 unsigned short logical_address; } __attribute__((packed)); @@ -96,9 +96,9 @@ struct ms_register { struct mspro_param_register { unsigned char system; -#define MEMSTICK_SYS_SERIAL 0x80 #define MEMSTICK_SYS_PAR4 0x00 #define MEMSTICK_SYS_PAR8 0x40 +#define MEMSTICK_SYS_SERIAL 0x80 unsigned short data_count; unsigned int data_address; @@ -147,7 +147,7 @@ struct ms_register_addr { unsigned char w_length; } __attribute__((packed)); -enum { +enum memstick_tpc { MS_TPC_READ_MG_STATUS = 0x01, MS_TPC_READ_LONG_DATA = 0x02, MS_TPC_READ_SHORT_DATA = 0x03, @@ -167,7 +167,7 @@ enum { MS_TPC_SET_CMD = 0x0e }; -enum { +enum memstick_command { MS_CMD_BLOCK_END = 0x33, MS_CMD_RESET = 0x3c, MS_CMD_BLOCK_WRITE = 0x55, @@ -201,8 +201,6 @@ enum { /*** Driver structures and functions ***/ -#define MEMSTICK_PART_SHIFT 3 - enum memstick_param { MEMSTICK_POWER = 1, MEMSTICK_INTERFACE }; #define MEMSTICK_POWER_OFF 0 @@ -215,24 +213,27 @@ enum memstick_param { MEMSTICK_POWER = 1, MEMSTICK_INTERFACE }; struct memstick_host; struct memstick_driver; +struct memstick_device_id { + unsigned char match_flags; #define MEMSTICK_MATCH_ALL 0x01 + unsigned char type; #define MEMSTICK_TYPE_LEGACY 0xff #define MEMSTICK_TYPE_DUO 0x00 #define MEMSTICK_TYPE_PRO 0x01 + unsigned char category; #define MEMSTICK_CATEGORY_STORAGE 0xff #define MEMSTICK_CATEGORY_STORAGE_DUO 0x00 +#define MEMSTICK_CATEGORY_IO 0x01 +#define MEMSTICK_CATEGORY_IO_PRO 0x10 -#define MEMSTICK_CLASS_GENERIC 0xff -#define MEMSTICK_CLASS_GENERIC_DUO 0x00 - - -struct memstick_device_id { - unsigned char match_flags; - unsigned char type; - unsigned char category; unsigned char class; +#define MEMSTICK_CLASS_FLASH 0xff +#define MEMSTICK_CLASS_DUO 0x00 +#define MEMSTICK_CLASS_ROM 0x01 +#define MEMSTICK_CLASS_RO 0x02 +#define MEMSTICK_CLASS_WP 0x03 }; struct memstick_request { @@ -319,9 +320,9 @@ void memstick_suspend_host(struct memstick_host *host); void memstick_resume_host(struct memstick_host *host); void memstick_init_req_sg(struct memstick_request *mrq, unsigned char tpc, - struct scatterlist *sg); + const struct scatterlist *sg); void memstick_init_req(struct memstick_request *mrq, unsigned char tpc, - void *buf, size_t length); + const void *buf, size_t length); int memstick_next_req(struct memstick_host *host, struct memstick_request **mrq); void memstick_new_req(struct memstick_host *host); -- cgit v1.2.3 From 29bdc88384c2b24e37e5760df0dc898546083d6b Mon Sep 17 00:00:00 2001 From: Vladimir Sokolovsky Date: Mon, 15 Sep 2008 14:25:23 -0700 Subject: IB/mlx4: Fix up fast register page list format Byte swap the addresses in the page list for fast register work requests to big endian to match what the HCA expectx. Also, the addresses must have the "present" bit set so that the HCA knows it can access them. Otherwise the HCA will fault the first time it accesses the memory region. Signed-off-by: Vladimir Sokolovsky Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/qp.c | 6 ++++++ drivers/net/mlx4/mr.c | 2 -- include/linux/mlx4/device.h | 4 ++++ 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index f29dbb767e87..9559248f265b 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1342,6 +1342,12 @@ static __be32 convert_access(int acc) static void set_fmr_seg(struct mlx4_wqe_fmr_seg *fseg, struct ib_send_wr *wr) { struct mlx4_ib_fast_reg_page_list *mfrpl = to_mfrpl(wr->wr.fast_reg.page_list); + int i; + + for (i = 0; i < wr->wr.fast_reg.page_list_len; ++i) + wr->wr.fast_reg.page_list->page_list[i] = + cpu_to_be64(wr->wr.fast_reg.page_list->page_list[i] | + MLX4_MTT_FLAG_PRESENT); fseg->flags = convert_access(wr->wr.fast_reg.access_flags); fseg->mem_key = cpu_to_be32(wr->wr.fast_reg.rkey); diff --git a/drivers/net/mlx4/mr.c b/drivers/net/mlx4/mr.c index 644adf074a35..d1dd5b48dbd1 100644 --- a/drivers/net/mlx4/mr.c +++ b/drivers/net/mlx4/mr.c @@ -71,8 +71,6 @@ struct mlx4_mpt_entry { #define MLX4_MPT_PD_FLAG_RAE (1 << 28) #define MLX4_MPT_PD_FLAG_EN_INV (3 << 24) -#define MLX4_MTT_FLAG_PRESENT 1 - #define MLX4_MPT_STATUS_SW 0xF0 #define MLX4_MPT_STATUS_HW 0x00 diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 655ea0d1ee14..b2f944468313 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -141,6 +141,10 @@ enum { MLX4_STAT_RATE_OFFSET = 5 }; +enum { + MLX4_MTT_FLAG_PRESENT = 1 +}; + static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor) { return (major << 32) | (minor << 16) | subminor; -- cgit v1.2.3 From b08508c40adf3fd1330aabc4f37d3254179776c4 Mon Sep 17 00:00:00 2001 From: Greg KH Date: Tue, 26 Aug 2008 08:20:34 -0700 Subject: PCI: fix compiler warnings in pci_get_subsys() pci_get_subsys() changed in 2.6.26 so that the from pointer is modified when the call is being invoked, so fix up the 'const' marking of it that the compiler is complaining about. Reported-by: Rufus & Azrael Signed-off-by: Greg Kroah-Hartman Signed-off-by: Jesse Barnes --- drivers/pci/search.c | 6 +++--- include/linux/pci.h | 8 ++++---- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/search.c b/drivers/pci/search.c index 3b3b5f178797..4edfc4731bd4 100644 --- a/drivers/pci/search.c +++ b/drivers/pci/search.c @@ -162,7 +162,7 @@ EXPORT_SYMBOL(pci_find_slot); * time. */ struct pci_dev *pci_find_device(unsigned int vendor, unsigned int device, - const struct pci_dev *from) + struct pci_dev *from) { struct pci_dev *pdev; @@ -263,7 +263,7 @@ static int match_pci_dev_by_id(struct device *dev, void *data) * this file. */ static struct pci_dev *pci_get_dev_by_id(const struct pci_device_id *id, - const struct pci_dev *from) + struct pci_dev *from) { struct device *dev; struct device *dev_start = NULL; @@ -303,7 +303,7 @@ static struct pci_dev *pci_get_dev_by_id(const struct pci_device_id *id, */ struct pci_dev *pci_get_subsys(unsigned int vendor, unsigned int device, unsigned int ss_vendor, unsigned int ss_device, - const struct pci_dev *from) + struct pci_dev *from) { struct pci_dev *pdev; struct pci_device_id *id; diff --git a/include/linux/pci.h b/include/linux/pci.h index c0e14008a3c2..98dc6243a706 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -534,7 +534,7 @@ extern void pci_sort_breadthfirst(void); #ifdef CONFIG_PCI_LEGACY struct pci_dev __deprecated *pci_find_device(unsigned int vendor, unsigned int device, - const struct pci_dev *from); + struct pci_dev *from); struct pci_dev __deprecated *pci_find_slot(unsigned int bus, unsigned int devfn); #endif /* CONFIG_PCI_LEGACY */ @@ -550,7 +550,7 @@ struct pci_dev *pci_get_device(unsigned int vendor, unsigned int device, struct pci_dev *from); struct pci_dev *pci_get_subsys(unsigned int vendor, unsigned int device, unsigned int ss_vendor, unsigned int ss_device, - const struct pci_dev *from); + struct pci_dev *from); struct pci_dev *pci_get_slot(struct pci_bus *bus, unsigned int devfn); struct pci_dev *pci_get_bus_and_slot(unsigned int bus, unsigned int devfn); struct pci_dev *pci_get_class(unsigned int class, struct pci_dev *from); @@ -816,7 +816,7 @@ _PCI_NOP_ALL(write,) static inline struct pci_dev *pci_find_device(unsigned int vendor, unsigned int device, - const struct pci_dev *from) + struct pci_dev *from) { return NULL; } @@ -838,7 +838,7 @@ static inline struct pci_dev *pci_get_subsys(unsigned int vendor, unsigned int device, unsigned int ss_vendor, unsigned int ss_device, - const struct pci_dev *from) + struct pci_dev *from) { return NULL; } -- cgit v1.2.3 From ef3d7714f6b75b51825ad0384b5ce48358427e50 Mon Sep 17 00:00:00 2001 From: David Miller Date: Tue, 16 Sep 2008 15:00:11 -0700 Subject: Fix PNP build failure, bugzilla #11276 This fill fix the following regression list entry: Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=11276 Subject : build error: CONFIG_OPTIMIZE_INLINING=y causes gcc 4.2 to do stupid things Submitter : Randy Dunlap Date : 2008-08-06 17:18 (38 days old) References : http://marc.info/?l=linux-kernel&m=121804329014332&w=4 http://lkml.org/lkml/2008/7/22/353 Handled-By : Bjorn Helgaas Patch : http://lkml.org/lkml/2008/7/22/364 with what I believe is a better fix than the one referenced in the regression entry above. These PNP header interfaces try to work in such a way that you can reference some of them even if PNP is not enabled, and the compiler was expected to optimize everything away. Which is mostly fine, except that there was one interface for which there was not provided an inline "NOP" implementation. Once we add that, all of these compile failures cannot handle any more. pnp: Provide NOP inline implementation of pnp_get_resource() when !PNP Fixes kernel bugzilla #11276. Signed-off-by: David S. Miller Signed-off-by: Linus Torvalds --- include/linux/pnp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pnp.h b/include/linux/pnp.h index 1ce54b63085d..be764e514e35 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -21,7 +21,14 @@ struct pnp_dev; /* * Resource Management */ +#ifdef CONFIG_PNP struct resource *pnp_get_resource(struct pnp_dev *, unsigned int, unsigned int); +#else +static inline struct resource *pnp_get_resource(struct pnp_dev *dev, unsigned int type, unsigned int num) +{ + return NULL; +} +#endif static inline int pnp_resource_valid(struct resource *res) { -- cgit v1.2.3 From c32a162fd420fe8dfb049db941b2438061047fcc Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Mon, 22 Sep 2008 13:57:43 -0700 Subject: smb.h: do not include linux/time.h in userspace linux/time.h conflicts with time.h from glibc It breaks building smbmount from samba. It's regression introduced by commit 76308da (" smb.h: uses struct timespec but didn't include linux/time.h"). Signed-off-by: Kirill A. Shutemov Cc: [2.6.26.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/smb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smb.h b/include/linux/smb.h index caa43b2370cb..82fefddc5987 100644 --- a/include/linux/smb.h +++ b/include/linux/smb.h @@ -11,7 +11,9 @@ #include #include +#ifdef __KERNEL__ #include +#endif enum smb_protocol { SMB_PROTOCOL_NONE, -- cgit v1.2.3 From b4f151ff899362fec952c45d166252c9912c041f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 24 Sep 2008 17:48:26 +0100 Subject: MN10300: Move asm-arm/cnt32_to_63.h to include/linux/ Move asm-arm/cnt32_to_63.h to include/linux/ so that MN10300 can make use of it too. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- arch/arm/mach-pxa/time.c | 2 +- arch/arm/mach-sa1100/generic.c | 2 +- arch/arm/mach-versatile/core.c | 2 +- include/linux/cnt32_to_63.h | 80 ++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 83 insertions(+), 3 deletions(-) create mode 100644 include/linux/cnt32_to_63.h (limited to 'include/linux') diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c index 67e18509d7bf..b0d6b32654cf 100644 --- a/arch/arm/mach-pxa/time.c +++ b/arch/arm/mach-pxa/time.c @@ -17,9 +17,9 @@ #include #include #include +#include #include -#include #include #include #include diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c index 1362994c78aa..b422526f6d8b 100644 --- a/arch/arm/mach-sa1100/generic.c +++ b/arch/arm/mach-sa1100/generic.c @@ -18,9 +18,9 @@ #include #include /* just for sched_clock() - funny that */ #include +#include #include -#include #include #include #include diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c index d75e795c893e..b638f10411e8 100644 --- a/arch/arm/mach-versatile/core.c +++ b/arch/arm/mach-versatile/core.c @@ -28,8 +28,8 @@ #include #include #include +#include -#include #include #include #include diff --git a/include/linux/cnt32_to_63.h b/include/linux/cnt32_to_63.h new file mode 100644 index 000000000000..8c0f9505b48c --- /dev/null +++ b/include/linux/cnt32_to_63.h @@ -0,0 +1,80 @@ +/* + * Extend a 32-bit counter to 63 bits + * + * Author: Nicolas Pitre + * Created: December 3, 2006 + * Copyright: MontaVista Software, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + +#ifndef __LINUX_CNT32_TO_63_H__ +#define __LINUX_CNT32_TO_63_H__ + +#include +#include +#include + +/* this is used only to give gcc a clue about good code generation */ +union cnt32_to_63 { + struct { +#if defined(__LITTLE_ENDIAN) + u32 lo, hi; +#elif defined(__BIG_ENDIAN) + u32 hi, lo; +#endif + }; + u64 val; +}; + + +/** + * cnt32_to_63 - Expand a 32-bit counter to a 63-bit counter + * @cnt_lo: The low part of the counter + * + * Many hardware clock counters are only 32 bits wide and therefore have + * a relatively short period making wrap-arounds rather frequent. This + * is a problem when implementing sched_clock() for example, where a 64-bit + * non-wrapping monotonic value is expected to be returned. + * + * To overcome that limitation, let's extend a 32-bit counter to 63 bits + * in a completely lock free fashion. Bits 0 to 31 of the clock are provided + * by the hardware while bits 32 to 62 are stored in memory. The top bit in + * memory is used to synchronize with the hardware clock half-period. When + * the top bit of both counters (hardware and in memory) differ then the + * memory is updated with a new value, incrementing it when the hardware + * counter wraps around. + * + * Because a word store in memory is atomic then the incremented value will + * always be in synch with the top bit indicating to any potential concurrent + * reader if the value in memory is up to date or not with regards to the + * needed increment. And any race in updating the value in memory is harmless + * as the same value would simply be stored more than once. + * + * The only restriction for the algorithm to work properly is that this + * code must be executed at least once per each half period of the 32-bit + * counter to properly update the state bit in memory. This is usually not a + * problem in practice, but if it is then a kernel timer could be scheduled + * to manage for this code to be executed often enough. + * + * Note that the top bit (bit 63) in the returned value should be considered + * as garbage. It is not cleared here because callers are likely to use a + * multiplier on the returned value which can get rid of the top bit + * implicitly by making the multiplier even, therefore saving on a runtime + * clear-bit instruction. Otherwise caller must remember to clear the top + * bit explicitly. + */ +#define cnt32_to_63(cnt_lo) \ +({ \ + static volatile u32 __m_cnt_hi; \ + union cnt32_to_63 __x; \ + __x.hi = __m_cnt_hi; \ + __x.lo = (cnt_lo); \ + if (unlikely((s32)(__x.hi ^ __x.lo) < 0)) \ + __m_cnt_hi = __x.hi = (__x.hi ^ 0x80000000) + (__x.hi >> 31); \ + __x.val; \ +}) + +#endif -- cgit v1.2.3 From b00c1a99e7758f794923c61e5cd55268d61c9469 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 29 Sep 2008 15:44:46 +0200 Subject: hrtimer: mark migration state Impact: during migration active hrtimers can be seen as inactive The migration code removes the hrtimers from the queues of the dead CPU and sets the state temporary to INACTIVE. The enqueue code sets it to ACTIVE/PENDING again. Prevent that the wrong state can be seen by using a separate migration state bit. Signed-off-by: Thomas Gleixner --- include/linux/hrtimer.h | 4 +++- kernel/hrtimer.c | 12 ++++++++++-- 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 6d93dce61cbb..bdd88df1b4e5 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -67,9 +67,10 @@ enum hrtimer_cb_mode { * 0x02 callback function running * 0x04 callback pending (high resolution mode) * - * Special case: + * Special cases: * 0x03 callback function running and enqueued * (was requeued on another CPU) + * 0x09 timer was migrated on CPU hotunplug * The "callback function running and enqueued" status is only possible on * SMP. It happens for example when a posix timer expired and the callback * queued a signal. Between dropping the lock which protects the posix timer @@ -87,6 +88,7 @@ enum hrtimer_cb_mode { #define HRTIMER_STATE_ENQUEUED 0x01 #define HRTIMER_STATE_CALLBACK 0x02 #define HRTIMER_STATE_PENDING 0x04 +#define HRTIMER_STATE_MIGRATE 0x08 /** * struct hrtimer - the basic hrtimer structure diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index ac2f6d6d4868..ace723dd1e52 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1602,7 +1602,13 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base, timer = rb_entry(node, struct hrtimer, node); BUG_ON(hrtimer_callback_running(timer)); debug_hrtimer_deactivate(timer); - __remove_hrtimer(timer, old_base, HRTIMER_STATE_INACTIVE, 0); + + /* + * Mark it as STATE_MIGRATE not INACTIVE otherwise the + * timer could be seen as !active and just vanish away + * under us on another CPU + */ + __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0); timer->base = new_base; /* * Enqueue the timer. Allow reprogramming of the event device @@ -1620,13 +1626,15 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base, * state, we need to do that otherwise we end up with * a stale timer. */ - if (timer->state == HRTIMER_STATE_INACTIVE) { + if (timer->state == HRTIMER_STATE_MIGRATE) { timer->state = HRTIMER_STATE_PENDING; list_add_tail(&timer->cb_entry, &new_base->cpu_base->cb_pending); raise = 1; } #endif + /* Clear the migration state bit */ + timer->state &= ~HRTIMER_STATE_MIGRATE; } return raise; } -- cgit v1.2.3 From ccc7dadf736639da86f3e0c86832c11a66fc8221 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 29 Sep 2008 15:47:42 +0200 Subject: hrtimer: prevent migration of per CPU hrtimers Impact: per CPU hrtimers can be migrated from a dead CPU The hrtimer code has no knowledge about per CPU timers, but we need to prevent the migration of such timers and warn when such a timer is active at migration time. Explicitely mark the timers as per CPU and use a more understandable mode descriptor for the interrupts safe unlocked callback mode, which is used by hrtimer_sleeper and the scheduler code. Signed-off-by: Thomas Gleixner --- include/linux/hrtimer.h | 14 +++++++++++--- kernel/hrtimer.c | 37 +++++++++++++++++++++++++------------ kernel/sched.c | 4 ++-- kernel/time/tick-sched.c | 2 +- kernel/trace/trace_sysprof.c | 2 +- 5 files changed, 40 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index bdd88df1b4e5..2f245fe63bda 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -47,14 +47,22 @@ enum hrtimer_restart { * HRTIMER_CB_IRQSAFE: Callback may run in hardirq context * HRTIMER_CB_IRQSAFE_NO_RESTART: Callback may run in hardirq context and * does not restart the timer - * HRTIMER_CB_IRQSAFE_NO_SOFTIRQ: Callback must run in hardirq context - * Special mode for tick emultation + * HRTIMER_CB_IRQSAFE_PERCPU: Callback must run in hardirq context + * Special mode for tick emulation and + * scheduler timer. Such timers are per + * cpu and not allowed to be migrated on + * cpu unplug. + * HRTIMER_CB_IRQSAFE_UNLOCKED: Callback should run in hardirq context + * with timer->base lock unlocked + * used for timers which call wakeup to + * avoid lock order problems with rq->lock */ enum hrtimer_cb_mode { HRTIMER_CB_SOFTIRQ, HRTIMER_CB_IRQSAFE, HRTIMER_CB_IRQSAFE_NO_RESTART, - HRTIMER_CB_IRQSAFE_NO_SOFTIRQ, + HRTIMER_CB_IRQSAFE_PERCPU, + HRTIMER_CB_IRQSAFE_UNLOCKED, }; /* diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index ace723dd1e52..cdec83e722fa 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -672,13 +672,14 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, */ BUG_ON(timer->function(timer) != HRTIMER_NORESTART); return 1; - case HRTIMER_CB_IRQSAFE_NO_SOFTIRQ: + case HRTIMER_CB_IRQSAFE_PERCPU: + case HRTIMER_CB_IRQSAFE_UNLOCKED: /* * This is solely for the sched tick emulation with * dynamic tick support to ensure that we do not * restart the tick right on the edge and end up with * the tick timer in the softirq ! The calling site - * takes care of this. + * takes care of this. Also used for hrtimer sleeper ! */ debug_hrtimer_deactivate(timer); return 1; @@ -1245,7 +1246,8 @@ static void __run_hrtimer(struct hrtimer *timer) timer_stats_account_hrtimer(timer); fn = timer->function; - if (timer->cb_mode == HRTIMER_CB_IRQSAFE_NO_SOFTIRQ) { + if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU || + timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED) { /* * Used for scheduler timers, avoid lock inversion with * rq->lock and tasklist_lock. @@ -1452,7 +1454,7 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) sl->timer.function = hrtimer_wakeup; sl->task = task; #ifdef CONFIG_HIGH_RES_TIMERS - sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; + sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED; #endif } @@ -1592,7 +1594,7 @@ static void __cpuinit init_hrtimers_cpu(int cpu) #ifdef CONFIG_HOTPLUG_CPU static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base, - struct hrtimer_clock_base *new_base) + struct hrtimer_clock_base *new_base, int dcpu) { struct hrtimer *timer; struct rb_node *node; @@ -1603,6 +1605,18 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base, BUG_ON(hrtimer_callback_running(timer)); debug_hrtimer_deactivate(timer); + /* + * Should not happen. Per CPU timers should be + * canceled _before_ the migration code is called + */ + if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU) { + __remove_hrtimer(timer, old_base, + HRTIMER_STATE_INACTIVE, 0); + WARN(1, "hrtimer (%p %p)active but cpu %d dead\n", + timer, timer->function, dcpu); + continue; + } + /* * Mark it as STATE_MIGRATE not INACTIVE otherwise the * timer could be seen as !active and just vanish away @@ -1619,12 +1633,11 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base, /* * Happens with high res enabled when the timer was * already expired and the callback mode is - * HRTIMER_CB_IRQSAFE_NO_SOFTIRQ - * (hrtimer_sleeper). The enqueue code does not move - * them to the soft irq pending list for - * performance/latency reasons, but in the migration - * state, we need to do that otherwise we end up with - * a stale timer. + * HRTIMER_CB_IRQSAFE_UNLOCKED (hrtimer_sleeper). The + * enqueue code does not move them to the soft irq + * pending list for performance/latency reasons, but + * in the migration state, we need to do that + * otherwise we end up with a stale timer. */ if (timer->state == HRTIMER_STATE_MIGRATE) { timer->state = HRTIMER_STATE_PENDING; @@ -1682,7 +1695,7 @@ static void migrate_hrtimers(int cpu) for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { if (migrate_hrtimer_list(&old_base->clock_base[i], - &new_base->clock_base[i])) + &new_base->clock_base[i], cpu)) raise = 1; } diff --git a/kernel/sched.c b/kernel/sched.c index 13dd2db9fb2d..ad1962dc0aa2 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -201,7 +201,7 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); rt_b->rt_period_timer.function = sched_rt_period_timer; - rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; + rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED; } static void start_rt_bandwidth(struct rt_bandwidth *rt_b) @@ -1119,7 +1119,7 @@ static void init_rq_hrtick(struct rq *rq) hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); rq->hrtick_timer.function = hrtick; - rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; + rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU; } #else static inline void hrtick_clear(struct rq *rq) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 39019b3f7621..cb02324bdb88 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -625,7 +625,7 @@ void tick_setup_sched_timer(void) */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ts->sched_timer.function = tick_sched_timer; - ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; + ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU; /* Get the next period (per cpu) */ ts->sched_timer.expires = tick_init_jiffy_update(); diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c index bb948e52ce20..db58fb66a135 100644 --- a/kernel/trace/trace_sysprof.c +++ b/kernel/trace/trace_sysprof.c @@ -202,7 +202,7 @@ static void start_stack_timer(int cpu) hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = stack_trace_timer_fn; - hrtimer->cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; + hrtimer->cb_mode = HRTIMER_CB_IRQSAFE_PERCPU; hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL); } -- cgit v1.2.3 From 4b19de6d1cb07c8bcb6778e771f9cfd5bcfdfd3e Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Thu, 2 Oct 2008 14:50:16 -0700 Subject: mm: tiny-shmem nommu fix The previous patch db203d53d474aa068984e409d807628f5841da1b ("mm: tiny-shmem fix lock ordering: mmap_sem vs i_mutex") to fix the lock ordering in tiny-shmem breaks shared anonymous and IPC memory on NOMMU architectures because it was using the expanding truncate to signal ramfs to allocate a physically contiguous RAM backing the inode (otherwise it is unusable for "memory mapping" it to userspace). However do_truncate is what caused the lock ordering error, due to it taking i_mutex. In this case, we can actually just call ramfs directly to allocate memory for the mapping, rather than go via truncate. Acked-by: David Howells Acked-by: Hugh Dickins Signed-off-by: Nick Piggin Cc: Matt Mackall Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ramfs/file-nommu.c | 2 +- include/linux/ramfs.h | 1 + mm/tiny-shmem.c | 6 ++++++ 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 52312ec93ff4..5145cb9125af 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -58,7 +58,7 @@ const struct inode_operations ramfs_file_inode_operations = { * size 0 on the assumption that it's going to be used for an mmap of shared * memory */ -static int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) +int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) { struct pagevec lru_pvec; unsigned long npages, xpages, loop, limit; diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index b160fb18e8d6..37aaf2b39863 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -6,6 +6,7 @@ extern int ramfs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt); #ifndef CONFIG_MMU +extern int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize); extern unsigned long ramfs_nommu_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, diff --git a/mm/tiny-shmem.c b/mm/tiny-shmem.c index d17cb6f6ab10..8d7a27a6335c 100644 --- a/mm/tiny-shmem.c +++ b/mm/tiny-shmem.c @@ -80,6 +80,12 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) inode->i_nlink = 0; /* It is unlinked */ init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ, &ramfs_file_operations); + +#ifndef CONFIG_MMU + error = ramfs_nommu_expand_for_mapping(inode, size); + if (error) + goto close_file; +#endif return file; close_file: -- cgit v1.2.3 From 897312bd240357c88ce906633703c324c6f0a5cd Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 3 Oct 2008 15:23:41 -0700 Subject: include/linux/stacktrace.h: declare struct task_struct include/linux/stacktrace.h:13: warning: 'struct task_struct' declared inside parameter list (This might be a hard error on sparc64, which uses this header and has -Werror) Reported-by: "Randy.Dunlap" Acked-by: Ingo Molnar Cc: Peter Zijlstra Cc: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stacktrace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 5da9794b2d78..b106fd8e0d5c 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -1,6 +1,8 @@ #ifndef __LINUX_STACKTRACE_H #define __LINUX_STACKTRACE_H +struct task_struct; + #ifdef CONFIG_STACKTRACE struct stack_trace { unsigned int nr_entries, max_entries; -- cgit v1.2.3 From f20f258603ebc5da91e76884cf0c0d7ac9804b1c Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Sun, 5 Oct 2008 18:23:27 +0200 Subject: ide-cd: temporary tray close fix This one fixes http://bugzilla.kernel.org/show_bug.cgi?id=11602. A more generic fix for drives which cannot autoclose tray will follow. Signed-off-by: Borislav Petkov Cc: Jens Axboe [bart: add an extra parentheses for consistency with the rest of kernel code] Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/ide/ide-cd.c | 5 ++++- include/linux/ide.h | 4 +++- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 49a8c589e346..e1cd7d520fc0 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -1661,7 +1661,9 @@ static int ide_cdrom_probe_capabilities(ide_drive_t *drive) cdi->mask &= ~CDC_PLAY_AUDIO; mechtype = buf[8 + 6] >> 5; - if (mechtype == mechtype_caddy || mechtype == mechtype_popup) + if (mechtype == mechtype_caddy || + mechtype == mechtype_popup || + (drive->atapi_flags & IDE_AFLAG_NO_AUTOCLOSE)) cdi->mask |= CDC_CLOSE_TRAY; if (cdi->sanyo_slot > 0) { @@ -1859,6 +1861,7 @@ static const struct cd_list_entry ide_cd_quirks_list[] = { { "MATSHITADVD-ROM SR-8176", NULL, IDE_AFLAG_PLAY_AUDIO_OK }, { "MATSHITADVD-ROM SR-8174", NULL, IDE_AFLAG_PLAY_AUDIO_OK }, { "Optiarc DVD RW AD-5200A", NULL, IDE_AFLAG_PLAY_AUDIO_OK }, + { "Optiarc DVD RW AD-7543A", NULL, IDE_AFLAG_NO_AUTOCLOSE }, { NULL, NULL, 0 } }; diff --git a/include/linux/ide.h b/include/linux/ide.h index 1524829f73f2..6514db8fd2e4 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -366,7 +366,9 @@ enum { /* Currently on a filemark */ IDE_AFLAG_FILEMARK = (1 << 25), /* 0 = no tape is loaded, so we don't rewind after ejecting */ - IDE_AFLAG_MEDIUM_PRESENT = (1 << 26) + IDE_AFLAG_MEDIUM_PRESENT = (1 << 26), + + IDE_AFLAG_NO_AUTOCLOSE = (1 << 27), }; struct ide_drive_s { -- cgit v1.2.3